ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfer
This addresses the challenge of separating style and content in images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of disentangling artistic style from semantic content in visual representation learning, achieving state-of-the-art results on disentangled metrics and downstream applications.
Representation learning aims to discover individual salient features of a domain in a compact and descriptive form that strongly identifies the unique characteristics of a given sample respective to its domain. Existing works in visual style representation literature have tried to disentangle style from content during training explicitly. A complete separation between these has yet to be fully achieved. Our paper aims to learn a representation of visual artistic style more strongly disentangled from the semantic content depicted in an image. We use Neural Style Transfer (NST) to measure and drive the learning signal and achieve state-of-the-art representation learning on explicitly disentangled metrics. We show that strongly addressing the disentanglement of style and content leads to large gains in style-specific metrics, encoding far less semantic information and achieving state-of-the-art accuracy in downstream multimodal applications.